Takuya Koriyama

2 accepted papers

2026

Precise Asymptotics of Bagging Regularized M-estimators

Takuya Koriyama, Pratik Patil, Jin-Hong Du, Kai Tan, Pierre C Bellec

ICML 2026poster

We characterize the squared prediction risk of ensemble estimators obtained through subagging (subsample bootstrap aggregating) regularized M-estimators and construct a consistent estimator for the risk. Specifically, we consider a heterogeneous collection of M?1 regularized M-estimators, each train…

Cited by 5 Source ↗Scholar ↗

2025

Phase transitions for the existence of unregularized M-estimators in single index models

Takuya Koriyama, Pierre C Bellec

ICML 2025poster

This paper studies phase transitions for the existence of unregularized M-estimators under proportional asymptotics where the sample size $n$ and feature dimension $p$ grow proportionally with $n/p \to \delta \in (1, \infty)$. We study the existence of M-estimators in single-index models where the r…

Cited by 0 Source ↗PDF ↗Scholar ↗